Forecasting the term structure of volatility of crude oil price changes

Peer reviewed

Electoral Volatility, Political Sophistication, Trust and Efficacy

In this article we investigate voter volatility and analyze the causes and motives of switching vote intentions. We test two main sets of variables linked to volatility in literature; political sophistication and ‘political (dis)satisfaction’. Results show that voters with low levels of political efficacy tend to switch more often, both within a campaign and between elections. In the analysis we differentiate between campaign volatility and inter-election volatility and by doing so show that the dynamics of a campaign have a profound impact on volatility. The campaign period is when the lowly sophisticated switch their vote intention. Those with higher levels of interest in politics have switched their intention before the campaign has started. The data for this analysis are from the three wave PartiRep Belgian Election Study (2009).

Algorithms for Geometric Matching, Clustering, and Covering

With the popularization of GPS-enabled devices such as mobile phones, location data are becoming available at an unprecedented scale. The locations may be collected from many different sources such as vehicles moving around a city, user check-ins in social networks, and geo-tagged micro-blogging photos or messages. Besides the longitude and latitude, each location record may also have a timestamp and additional information such as the name of the location. Time-ordered sequences of these locations form trajectories, which together contain useful high-level information about people's movement patterns.

The first part of this thesis focuses on a few geometric problems motivated by the matching and clustering of trajectories. We first give a new algorithm for computing a matching between a pair of curves under existing models such as dynamic time warping (DTW). The algorithm is more efficient than standard dynamic programming algorithms both theoretically and practically. We then propose a new matching model for trajectories that avoids the drawbacks of existing models. For trajectory clustering, we present an algorithm that computes clusters of subtrajectories, which correspond to common movement patterns. We also consider trajectories of check-ins, and propose a statistical generative model, which identifies check-in clusters as well as the transition patterns between the clusters.

The second part of the thesis considers the problem of covering shortest paths in a road network, motivated by an EV charging station placement problem. More specifically, a subset of vertices in the road network are selected to place charging stations so that every shortest path contains enough charging stations and can be traveled by an EV without draining the battery. We first introduce a general technique for the geometric set cover problem. This technique leads to near-linear-time approximation algorithms, which are the state-of-the-art algorithms for this problem in either running time or approximation ratio. We then use this technique to develop a near-linear-time algorithm for this

shortest-path cover problem.

Rise, fragmentation, infringement and fear: emerging urban issues in Chinese clustering in Italy

China is today facing rapid economic development and the long-term implications of China’s rise for European economy, society and culture, are constantly debated but still almost unknown. Moreover, only recently a new volume edited by Kunzmann has clearly pointed out a particular field of research like the EU spatial impact of China’s convergence in the global market. The aim of the present paper is to deal with the spatial issues related to the growing Chinese communities, especially in Italy, that are part of a more general and considerable transformation process of the traditional Chinese enclaves in EU cities: from recognizable “Chinatowns” to new hybrid urban formations where housing, retail, wholesale and even commodity production often tend to match. Key-Concepts like rise, fragmentation, infringement and fear are useful in analysing some of the more controversial socio-economic dynamics of Chinese clusters especially in a traditionally manufactured-based country like Italy, where it’s recognizable a unique paradox of a “double competition” from outside and from inside. This statement poses a serious threat to local economic systems in terms of sustainability and social cohesion, making it necessary to rethink the role and the nature of public action in facing new forms of marginality at urban and regional level.

Clustering in non-parametric multivariate analyses.

Non-parametric multivariate analyses of complex ecological datasets are widely used. Following appropriate pre-treatment of the data inter-sample resemblances are calculated using appropriate measures. Ordination and clustering derived from these resemblances are used to visualise relationships among samples (or variables). Hierarchical agglomerative clustering with group-average (UPGMA) linkage is often the clustering method chosen. Using an example dataset of zooplankton densities from the Bristol Channel and Severn Estuary, UK, a range of existing and new clustering methods are applied and the results compared. Although the examples focus on analysis of samples, the methods may also be applied to species analysis. Dendrograms derived by hierarchical clustering are compared using cophenetic correlations, which are also used to determine optimum  in flexible beta clustering. A plot of cophenetic correlation against original dissimilarities reveals that a tree may be a poor representation of the full multivariate information. UNCTREE is an unconstrained binary divisive clustering algorithm in which values of the ANOSIM R statistic are used to determine (binary) splits in the data, to form a dendrogram. A form of flat clustering, k-R clustering, uses a combination of ANOSIM R and Similarity Profiles (SIMPROF) analyses to determine the optimum value of k, the number of groups into which samples should be clustered, and the sample membership of the groups. Robust outcomes from the application of such a range of differing techniques to the same resemblance matrix, as here, result in greater confidence in the validity of a clustering approach.

Clustering in non-parametric multivariate analyses.

Non-parametric multivariate analyses of complex ecological datasets are widely used. Following appropriate pre-treatment of the data inter-sample resemblances are calculated using appropriate measures. Ordination and clustering derived from these resemblances are used to visualise relationships among samples (or variables). Hierarchical agglomerative clustering with group-average (UPGMA) linkage is often the clustering method chosen. Using an example dataset of zooplankton densities from the Bristol Channel and Severn Estuary, UK, a range of existing and new clustering methods are applied and the results compared. Although the examples focus on analysis of samples, the methods may also be applied to species analysis. Dendrograms derived by hierarchical clustering are compared using cophenetic correlations, which are also used to determine optimum  in flexible beta clustering. A plot of cophenetic correlation against original dissimilarities reveals that a tree may be a poor representation of the full multivariate information. UNCTREE is an unconstrained binary divisive clustering algorithm in which values of the ANOSIM R statistic are used to determine (binary) splits in the data, to form a dendrogram. A form of flat clustering, k-R clustering, uses a combination of ANOSIM R and Similarity Profiles (SIMPROF) analyses to determine the optimum value of k, the number of groups into which samples should be clustered, and the sample membership of the groups. Robust outcomes from the application of such a range of differing techniques to the same resemblance matrix, as here, result in greater confidence in the validity of a clustering approach.

Extracting Patterns from Educational Traces via Clustering and Associated Quality Metrics

Clustering algorithms, pattern mining techniques and associated quality metrics emerged as reliable methods for modeling learners’ performance, comprehension and interaction in given educational scenarios. The specificity of available data such as missing values, extreme values or outliers, creates a challenge to extract significant user models from an educational perspective. In this paper we introduce a pattern detection mechanism with-in our data analytics tool based on k-means clustering and on SSE, silhouette, Dunn index and Xi-Beni index quality metrics. Experiments performed on a dataset obtained from our online e-learning platform show that the extracted interaction patterns were representative in classifying learners. Furthermore, the performed monitoring activities created a strong basis for generating automatic feedback to learners in terms of their course participation, while relying on their previous performance. In addition, our analysis introduces automatic triggers that highlight learners who will potentially fail the course, enabling tutors to take timely actions.

MixKMeans: Clustering Question-Answer Archives

Community-driven Question Answering (CQA) systems that crowdsource experiential information in the form of questions and answers and have accumulated valuable reusable knowledge. Clustering of QA datasets from CQA systems provides a means of organizing the content to ease tasks such as manual curation and tagging. In this paper, we present a clustering method that exploits the two-part question-answer structure in QA datasets to improve clustering quality. Our method, {\it MixKMeans}, composes question and answer space similarities in a way that the space on which the match is higher is allowed to dominate. This construction is motivated by our observation that semantic similarity between question-answer data (QAs) could get localized in either space. We empirically evaluate our method on a variety of real-world labeled datasets. Our results indicate that our method significantly outperforms state-of-the-art clustering methods for the task of clustering question-answer archives.

Abnormal Pedestrian Trajectory analysis based on arbitrary-length clustering

This papers examines the use of trajectory distance measures and clustering techniques to define normal
and abnormal trajectories in the context of pedestrian tracking in public spaces. In order to detect abnormal
trajectories, what is meant by a normal trajectory in a given scene is firstly defined. Then every trajectory
that deviates from this normality is classified as abnormal. By combining Dynamic Time Warping and a
modified K-Means algorithms for arbitrary-length data series, we have developed an algorithm for trajectory
clustering and abnormality detection. The final system performs with an overall accuracy of 83% and 75%
when tested in two different standard datasets.

Respiratory virus-associated severe acute respiratory illness (SARI) and viral clustering in Malawian children in a setting with a high prevalence of HIV, malaria and malnutrition

BACKGROUND:  We used four years of paediatric severe acute respiratory illness (SARI) sentinel surveillance in Blantyre, Malawi to identify factors associated with clinical severity and co-viral clustering.

METHODS:  From January 2011 to December 2014, 2363 children aged 3 months to 14 years presenting to hospital with SARI were enrolled. Nasopharyngeal aspirates were tested for influenza and other respiratory viruses. We assessed risk factors for clinical severity and conducted clustering analysis to identify viral clusters in children with co-viral detection.

RESULTS:  Hospital-attended influenza-positive SARI incidence was 2.0 cases per 10,000 children annually; it was highest children aged under 1 year (6.3 cases per 10,000), and HIV-infected children aged 5 to 9 years (6.0 cases per 10,000). 605 (26.8%) SARI cases had warning signs, which were positively associated with HIV infection (adjusted risk ratio [aRR]: 2.4, 95% CI: 1.4, 3.9), RSV infection (aRR: 1.9, 95% CI: 1.3, 3.0) and rainy season (aRR: 2.4, 95% CI: 1.6, 3.8). We identified six co-viral clusters; one cluster was associated with SARI with warning signs.

CONCLUSIONS:  Influenza vaccination may benefit young children and HIV infected children in this setting. Viral clustering may be associated with SARI severity; its assessment should be included in routine SARI surveillance.

Clustering-based Query Routing in Cooperative Semi-structured Peer to Peer Networks

We consider the problem of resource selection in clustered Peer-to-Peer Information Retrieval (P2P IR) networks with cooperative peers. The clustered P2P IR framework presents a significant departure from general P2P IR architectures by employing clustering to ensure content coherence between resources at the resource selection layer, without disturbing document allocation. We propose that such a property could be leveraged in resource selection by adapting well-studied and popular inverted lists for centralized document retrieval. Accordingly, we propose the Inverted PeerCluster Index (IPI), an approach that adapts the inverted lists, in a straightforward manner, for resource selection in clustered P2P IR. IPI also encompasses a strikingly simple peer-specific scoring mechanism that exploits the said index for resource selection. Through an extensive empirical analysis on P2P IR testbeds, we establish that IPI competes well with the sophisticated state-of-the-art methods in virtually every parameter of interest for the resource selection task, in the context of clustered P2P IR.

Effect of Earnings Volatility on Cost of Debt: The case of Swedish Limited Companies

The paper empirically tests the relationship between earnings volatility and cost of debt with a sample of more than 77,000 Swedish limited companies over the period 2006 to 2013 observing more than 677,000 firm years. As called upon by many researchers recently that there is very limited evidence of the association between earnings volatility and cost of debt this paper contributes greatly to the existing literature of earnings quality and debt contracts, especially on the consequence of earnings quality in the debt market. Earnings volatility is a proxy used for earnings quality while cost of debt is a component of debt contract. After controlling for firms’ profitability, liquidity, solvency, cashflow volatility, accruals volatility, sales volatility, business risk, financial risk and size this paper studies the effect of earnings volatility measured by standard deviation of Earnings Before Interest, Taxes, Depreciation and Amortization (EBITDA) on Cost of Debt. Overall finding suggests that lenders in Sweden does take earnings volatility into consideration while determining cost of debt for borrowers. But a deeper analysis of various industries suggest earnings volatility is not consistently used by lenders across all the industries. Lenders in Sweden are rather more sensitive to borrowers’ financial risk across all the industries. It may also be stated that larger borrowers tend to secure loans at a lower interest rate, the results are consistent with majority of the industries. Swedish debt market appears to be well prepared for financial crises as the debt crisis seems to have no or little adverse effect borrowers’ cost of capital. This study is the only empirical evidence to study the association between earnings volatility and cost of debt. Prior indirect research suggests earnings volatility has a negative effect on cost debt (i.e. an increase in earnings volatility will increase firm’s cost of debt). Our direct evidence from the Swedish debt market is consistent for some industries including media, real estate activities, transportation & warehousing, and other consumer services.

LDA-TM : A two-step approach to twitter topic data clustering

The Twitter System is the biggest social network in the world, and everyday millions of tweets are posted and talked about, expressing various views and opinions. A large variety of research activities have been conducted to study how the opinions can be clustered and analyzed, so that some tendencies can be uncovered. Due to the inherent weaknesses of the tweets - very short texts and very informal styles of writing - it is rather hard to make an investigation of tweet data analysis giving results with good performance and accuracy. In this paper, we intend to attack the problem from another aspect - using a two-layer structure to analyze the twitter data: LDA with topic map modelling. The experimental results demonstrate that this approach shows a progress in twitter data analysis. However, more experiments with this method are expected in order to ensure that the accurate analytic results can be maintained.

A New Clustering Methodology for the Analysis of Sorted or Categorized Stimuli

This paper introduces a new stochastic clustering methodology devised for the analysis of categorized or sorted data. The methodology reveals consumers' common category knowledge as well as individual differences in using this knowledge for classifying brands in a designated product class. A small study involving the categorization of 28 brands of U.S. automobiles is presented where the results of the proposed methodology are compared with those obtained from KMEANS clustering. Finally, directions for future research are discussed.